Vehicle and power management using power over ethernet devices

Patent metadata

Field	Value
Publication number	US-12095575-B2
Application number	US-202217708396-A
Country	US
Kind code	B2
Filing date	Mar 30, 2022
Priority date	Mar 30, 2022
Publication date	Sep 17, 2024
Grant date	Sep 17, 2024

Abstract

A server for regulating power from a Power-over-Ethernet switch to a plurality of vision sensors includes the following operations. An evaluation of individual contributions that each of the plurality of vision sensors makes to operational efficiency of the vision system is performed. Information indicative of a degradation condition to the plurality of vision sensors is received from the plurality of vision sensors. An amount of power needed to be supplied from the switch to alleviate the degradation condition of the plurality of vision sensors is estimated based upon the information indicative of the degradation condition. A determination is made that a total amount of power supplied from the switch exceeds an available amount of power capable of being supplied from the switch. Power from the switch to the plurality of vision sensors is individually regulated in real-time using a prioritization determined according to the evaluation.

First claim

What is claimed is:

1. A computer-implemented method, within a remote controlled vehicle movement (RCVM) server, of regulating power from a Power-over-Ethernet (PoE) switch to a vision system including plurality of PoE vision sensors connected to the PoE switch, comprising:
performing, using a convolutional neural network, an evaluation of individual contributions that each of the plurality of PoE vision sensors makes to operational efficiency of the vision system;
receiving, from at least one of the plurality of PoE vision sensors, information indicative of a degradation condition to the at least one of the plurality of PoE vision sensors;
estimating, based upon the information indicative of the degradation condition, an amount of power needed to be supplied from the PoE switch to alleviate the degradation condition of the at least one of the plurality of PoE vision sensors;
making a determination that a total amount of power supplied from the PoE switch exceeds an available amount of power capable of being supplied from the PoE switch; and
individually regulating in real-time, based upon the determination, power from the PoE switch to the plurality of PoE vision sensors using a prioritization determined according to the evaluation.

2. The method of claim 1 , wherein
the machine learning engine includes a convolutional neural network employing combinatorial padding and stride to progressively detect the degradation condition.

3. The method of claim 1 , wherein
the prioritization is based upon bin backing of power requirements for each of the plurality of PoE vision sensors based upon the evaluation.

4. The method of claim 1 , wherein
the estimating includes adjusting the amount of power needed to be supplied from the PoE switch based upon a determination that one of the plurality of PoE vision sensors having a degraded condition does not impact operational efficiency of the vision system.

5. The method of claim 1 , wherein
the estimating includes adjusting the amount of power needed to be supplied from the PoE switch based upon a determination that one of the plurality of PoE vision sensors having a degraded condition does not have a vehicle in range.

6. The method of claim 1 , wherein
each of the plurality of PoE vision sensors include at least one mitigation function.

7. The method of claim 6 , wherein
the individually regulating includes disabling the at least one mitigation function for a particular PoE vision sensor.

8. A remote controlled vehicle movement (RCVM) server including a computer hardware system configured to regulate power from a Power-over-Ethernet (PoE) switch to a vision system including plurality of PoE vision sensors connected to the PoE switch, comprising:
a hardware processor configured to perform the following executable operations:
performing, using a convolutional neural network, an evaluation of individual contributions that each of the plurality of PoE vision sensors makes to operational efficiency of the vision system;
receiving, from at least one of the plurality of PoE vision sensors, information indicative of a degradation condition to the at least one of the plurality of PoE vision sensors;
estimating, based upon the information indicative of the degradation condition, an amount of power needed to be supplied from the PoE switch to alleviate the degradation condition of the at least one of the plurality of PoE vision sensors;
making a determination that a total amount of power supplied from the PoE switch exceeds an available amount of power capable of being supplied from the PoE switch; and
individually regulating in real-time, based upon the determination, power from the PoE switch to the plurality of PoE vision sensors using a prioritization determined according to the evaluation.

9. The system of claim 8 , wherein
the machine learning engine includes a convolutional neural network employing combinatorial padding and stride to progressively detect the degradation condition.

10. The system of claim 8 , wherein
the prioritization is based upon bin backing of power requirements for each of the plurality of PoE vision sensors based upon the evaluation.

11. The system of claim 8 , wherein
the estimating includes adjusting the amount of power needed to be supplied from the PoE switch based upon a determination that one of the plurality of PoE vision sensors having a degraded condition does not impact operational efficiency of the vision system.

12. The system of claim 8 , wherein
the estimating includes adjusting the amount of power needed to be supplied from the PoE switch based upon a determination that one of the plurality of PoE vision sensors having a degraded condition does not have a vehicle in range.

13. The system of claim 8 , wherein
each of the plurality of PoE vision sensors include at least one mitigation function.

14. The system of claim 13 , wherein
the individually regulating includes disabling the at least one mitigation function for a particular PoE vision sensor.

15. A computer program product, comprising:
a computer readable storage medium having stored therein program code,
the program code, which when executed by a remote controlled vehicle movement (RCVM) server including a computer hardware system configured to regulate power from a Power-over-Ethernet (PoE) switch to a vision system including plurality of PoE vision sensors connected to the PoE switch, cause the computer hardware system to perform:
performing, using a convolutional neural network, an evaluation of individual contributions that each of the plurality of PoE vision sensors makes to operational efficiency of the vision system;
receiving, from at least one of the plurality of PoE vision sensors, information indicative of a degradation condition to the at least one of the plurality of PoE vision sensors;
estimating, based upon the information indicative of the degradation condition, an amount of power needed to be supplied from the PoE switch to alleviate the degradation condition of the at least one of the plurality of PoE vision sensors;
making a determination that a total amount of power supplied from the PoE switch exceeds an available amount of power capable of being supplied from the PoE switch; and
individually regulating in real-time, based upon the determination, power from the PoE switch to the plurality of PoE vision sensors using a prioritization determined according to the evaluation.

16. The computer program product of claim 15 , wherein
the machine learning engine includes a convolutional neural network employing combinatorial padding and stride to progressively detect the degradation condition.

17. The computer program product of claim 15 , wherein
the prioritization is based upon bin backing of power requirements for each of the plurality of PoE vision sensors based upon the evaluation.

18. The computer program product of claim 15 , wherein
the estimating includes adjusting the amount of power needed to be supplied from the PoE switch based upon a determination that one of the plurality of PoE vision sensors having a degraded condition does not impact operational efficiency of the vision system.

19. The computer program product of claim 15 , wherein
the estimating includes adjusting the amount of power needed to be supplied from the PoE switch based upon a determination that one of the plurality of PoE vision sensors having a degraded condition does not have a vehicle in range.

20. The computer program product of claim 15 ,

Assignees

• IBM

Inventors

• Baughman Aaron K
• Scott Debra
• Egger Michael
• Eggenberger Christian

Classifications

• G05D1/226

  Communication links with the remote-control arrangements · CPC title

• G05B13/027

  using neural networks only · CPC title

• G05D1/0022

  characterised by the communication link (data switching networks in general H04L12/00) · CPC title

• B62D15/0285

  Parking performed automatically · CPC title

• H04L12/10 Primary

  Current supply arrangements · CPC title